{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T11:20:59Z","timestamp":1783164059267,"version":"3.54.6"},"reference-count":103,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Council GRF","award":["14200218"],"award-info":[{"award-number":["14200218"]}]},{"name":"Hong Kong Research Council GRF","award":["14200220"],"award-info":[{"award-number":["14200220"]}]},{"name":"Hong Kong Research Council GRF","award":["14200021"],"award-info":[{"award-number":["14200021"]}]},{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","award":["ITS\/254\/19"],"award-info":[{"award-number":["ITS\/254\/19"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","award":["InP\/057\/21"],"award-info":[{"award-number":["InP\/057\/21"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3203891","type":"journal-article","created":{"date-parts":[[2022,9,2]],"date-time":"2022-09-02T19:53:50Z","timestamp":1662148430000},"page":"2900-2917","source":"Crossref","is-referenced-by-count":29,"title":["Bayesian Neural Network Language Modeling for Speech Recognition"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0731-3977","authenticated-orcid":false,"given":"Boyang","family":"Xue","sequence":"first","affiliation":[{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3345-6923","authenticated-orcid":false,"given":"Shoukang","family":"Hu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9650-0290","authenticated-orcid":false,"given":"Junhao","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7886-439X","authenticated-orcid":false,"given":"Mengzhe","family":"Geng","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6725-1160","authenticated-orcid":false,"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1999.0128"},{"key":"ref3","first-page":"1137","article-title":"A neural probabilistic language model","volume-title":"J. Mach. Learn. Res.","volume":"3","author":"Bengio","year":"2003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.09.003"},{"key":"ref5","first-page":"20","article-title":"Deep neural network language models","volume-title":"Proc. NAACL-HLT Workshop","author":"Arisoy","year":"2012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2215599"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2400218"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2598304"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2922048"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2225"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053399"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1164"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2770"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414477"},{"key":"ref16","article-title":"Advancing neural language modeling in automatic speech recognition","author":"Irie","year":"2020"},{"key":"ref17","article-title":"Transformer versus LSTM language models trained on uncertain ASR hypotheses in limited data scenarios","volume-title":"Proc. 13th Lang. Resour. Eval. Conf.","author":"Sheikh","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414076"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1053"},{"key":"ref22","article-title":"A structured self-attentive sentence embedding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1244"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref26","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Gehring","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2013-548"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638951"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-595"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2014-305"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053499"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref36","article-title":"Sequence transduction with recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Graves","year":"2012"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414784"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415039"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-211"},{"key":"ref42","first-page":"2814","article-title":"Understanding dropout","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baldi","year":"2013"},{"key":"ref43","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref44","first-page":"1027","article-title":"A theoretically grounded application of dropout in recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gal","year":"2016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/72.317730"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683066"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.1.108"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref50","first-page":"501","article-title":"On the solution of ill-posed problems and the method of regularization","author":"Tikhonov","year":"1963","journal-title":"Doklady Akademii Nauk."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078575"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2499302"},{"key":"ref53","volume-title":"Bayesian Learning for Neural Networks","volume":"118","author":"Neal","year":"2012"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.3.448"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5555\/2986459.2986721"},{"key":"ref57","first-page":"1613","article-title":"Weight uncertainty in neural network","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Blundell","year":"2015"},{"key":"ref58","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2013"},{"key":"ref59","first-page":"2980","article-title":"A recurrent latent variable model for sequential data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chung","year":"2015"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1823"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2379"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682487"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3069080"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682667"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3084072"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-51"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1030"},{"key":"ref68","article-title":"Bayesian recurrent neural networks","volume-title":"Proc. Women Mach. Learn. Workshop NIPS","author":"Fortunato","year":"2017"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683660"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1927"},{"key":"ref71","first-page":"14660","article-title":"Bayesian layers: A module for neural network uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tran","year":"2018"},{"key":"ref72","article-title":"BLT: Exact Bayesian inference with distribution transformers","author":"Yuan","year":"2019"},{"key":"ref73","first-page":"215","article-title":"Ensemble learning in Bayesian neural networks","volume":"168","author":"Barber","year":"1998","journal-title":"Nato ASI Ser. F. Comput. Syst. Sci."},{"key":"ref74","first-page":"1","article-title":"Stochastic gradient VB and the variational auto-encoder","volume-title":"Proc. 2nd Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_37"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref78","article-title":"Implementation of the standard I-vector system for the kaldi speech recognition toolkit","author":"Madikeri","year":"2016"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414046"},{"key":"ref82","article-title":"Bridging nonlinearities and stochastic regularizers with Gaussian error linear units","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks","year":"2016"},{"key":"ref83","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0745-0"},{"key":"ref85","first-page":"2575","article-title":"Variational dropout and the local reparameterization trick","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma","year":"2015"},{"key":"ref86","volume-title":"Gaussian Processes for Machine Learning","author":"Williams","year":"2006"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0745-0_2"},{"key":"ref88","article-title":"Steps toward deep kernel methods from infinite neural networks","author":"Hazan","year":"2015"},{"key":"ref89","article-title":"Deep neural networks as Gaussian processes","author":"Lee","year":"2017"},{"key":"ref90","first-page":"207","article-title":"Deep Gaussian processes","volume-title":"Proc. 16th Int. Conf. Artif. Intell. Statist.","author":"Damianou","year":"2013"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-832"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"ref93","first-page":"2020","article-title":"Neural architecture search with Bayesian optimisation and optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kandasamy","year":"2018"},{"key":"ref94","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zoph","year":"2017"},{"key":"ref95","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2018"},{"key":"ref96","article-title":"SNAS: Stochastic neural architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xie","year":"2019"},{"key":"ref97","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cai","year":"2018"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153253"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01210"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3078883"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266481"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2346"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09874985.pdf?arnumber=9874985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:41:55Z","timestamp":1706791315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9874985\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":103,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3203891","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}